Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from David Miller:

 1) Don't insert ESP trailer twice in IPSEC code, from Huy Nguyen.

 2) The default crypto algorithm selection in Kconfig for IPSEC is out
    of touch with modern reality, fix this up. From Eric Biggers.

 3) bpftool is missing an entry for BPF_MAP_TYPE_RINGBUF, from Andrii
    Nakryiko.

 4) Missing init of ->frame_sz in xdp_convert_zc_to_xdp_frame(), from
    Hangbin Liu.

 5) Adjust packet alignment handling in ax88179_178a driver to match
    what the hardware actually does. From Jeremy Kerr.

 6) register_netdevice can leak in the case one of the notifiers fail,
    from Yang Yingliang.

 7) Use after free in ip_tunnel_lookup(), from Taehee Yoo.

 8) VLAN checks in sja1105 DSA driver need adjustments, from Vladimir
    Oltean.

 9) tg3 driver can sleep forever when we get enough EEH errors, fix from
    David Christensen.

10) Missing {READ,WRITE}_ONCE() annotations in various Intel ethernet
    drivers, from Ciara Loftus.

11) Fix scanning loop break condition in of_mdiobus_register(), from
    Florian Fainelli.

12) MTU limit is incorrect in ibmveth driver, from Thomas Falcon.

13) Endianness fix in mlxsw, from Ido Schimmel.

14) Use after free in smsc95xx usbnet driver, from Tuomas Tynkkynen.

15) Missing bridge mrp configuration validation, from Horatiu Vultur.

16) Fix circular netns references in wireguard, from Jason A. Donenfeld.

17) PTP initialization on recovery is not done properly in qed driver,
    from Alexander Lobakin.

18) Endian conversion of L4 ports in filters of cxgb4 driver is wrong,
    from Rahul Lakkireddy.

19) Don't clear bound device TX queue of socket prematurely otherwise we
    get problems with ktls hw offloading, from Tariq Toukan.

20) ipset can do atomics on unaligned memory, fix from Russell King.

21) Align ethernet addresses properly in bridging code, from Thomas
    Martitz.

22) Don't advertise ipv4 addresses on SCTP sockets having ipv6only set,
    from Marcelo Ricardo Leitner.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (149 commits)
  rds: transport module should be auto loaded when transport is set
  sch_cake: fix a few style nits
  sch_cake: don't call diffserv parsing code when it is not needed
  sch_cake: don't try to reallocate or unshare skb unconditionally
  ethtool: fix error handling in linkstate_prepare_data()
  wil6210: account for napi_gro_receive never returning GRO_DROP
  hns: do not cast return value of napi_gro_receive to null
  socionext: account for napi_gro_receive never returning GRO_DROP
  wireguard: receive: account for napi_gro_receive never returning GRO_DROP
  vxlan: fix last fdb index during dump of fdb with nhid
  sctp: Don't advertise IPv4 addresses if ipv6only is set on the socket
  tc-testing: avoid action cookies with odd length.
  bpf: tcp: bpf_cubic: fix spurious HYSTART_DELAY exit upon drop in min RTT
  tcp_cubic: fix spurious HYSTART_DELAY exit upon drop in min RTT
  net: dsa: sja1105: fix tc-gate schedule with single element
  net: dsa: sja1105: recalculate gating subschedule after deleting tc-gate rules
  net: dsa: sja1105: unconditionally free old gating config
  net: dsa: sja1105: move sja1105_compose_gating_subschedule at the top
  net: macb: free resources on failure path of at91ether_open()
  net: macb: call pm_runtime_put_sync on failure path
  ...

5 files changed, 40 insertions, 22 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 6bc2388141f6..90b59fc50dc9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4192,10 +4192,12 @@ int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
 
 	local_bh_disable();
 
+	dev_xmit_recursion_inc();
 	HARD_TX_LOCK(dev, txq, smp_processor_id());
 	if (!netif_xmit_frozen_or_drv_stopped(txq))
 		ret = netdev_start_xmit(skb, dev, txq, false);
 	HARD_TX_UNLOCK(dev, txq);
+	dev_xmit_recursion_dec();
 
 	local_bh_enable();
 
@@ -9547,6 +9549,13 @@ int register_netdevice(struct net_device *dev)
 		rcu_barrier();
 
 		dev->reg_state = NETREG_UNREGISTERED;
+		/* We should put the kobject that hold in
+		 * netdev_unregister_kobject(), otherwise
+		 * the net device cannot be freed when
+		 * driver calls free_netdev(), because the
+		 * kobject is being hold.
+		 */
+		kobject_put(&dev->dev.kobj);
 	}
 	/*
 	 *	Prevent userspace races by waiting until the network
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 2ee7bc4c9e03..b09bebeadf0b 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -1721,3 +1721,4 @@ module_exit(exit_net_drop_monitor);
 MODULE_LICENSE("GPL v2");
 MODULE_AUTHOR("Neil Horman <nhorman@tuxdriver.com>");
 MODULE_ALIAS_GENL_FAMILY("NET_DM");
+MODULE_DESCRIPTION("Monitoring code for network dropped packet alerts");
diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c
index 0cfc35e6be28..b739cfab796e 100644
--- a/net/core/flow_offload.c
+++ b/net/core/flow_offload.c
@@ -372,14 +372,15 @@ int flow_indr_dev_register(flow_indr_block_bind_cb_t *cb, void *cb_priv)
 }
 EXPORT_SYMBOL(flow_indr_dev_register);
 
-static void __flow_block_indr_cleanup(flow_setup_cb_t *setup_cb, void *cb_priv,
+static void __flow_block_indr_cleanup(void (*release)(void *cb_priv),
+				      void *cb_priv,
 				      struct list_head *cleanup_list)
 {
 	struct flow_block_cb *this, *next;
 
 	list_for_each_entry_safe(this, next, &flow_block_indr_list, indr.list) {
-		if (this->cb == setup_cb &&
-		    this->cb_priv == cb_priv) {
+		if (this->release == release &&
+		    this->indr.cb_priv == cb_priv) {
 			list_move(&this->indr.list, cleanup_list);
 			return;
 		}
@@ -397,7 +398,7 @@ static void flow_block_indr_notify(struct list_head *cleanup_list)
 }
 
 void flow_indr_dev_unregister(flow_indr_block_bind_cb_t *cb, void *cb_priv,
-			      flow_setup_cb_t *setup_cb)
+			      void (*release)(void *cb_priv))
 {
 	struct flow_indr_dev *this, *next, *indr_dev = NULL;
 	LIST_HEAD(cleanup_list);
@@ -418,7 +419,7 @@ void flow_indr_dev_unregister(flow_indr_block_bind_cb_t *cb, void *cb_priv,
 		return;
 	}
 
-	__flow_block_indr_cleanup(setup_cb, cb_priv, &cleanup_list);
+	__flow_block_indr_cleanup(release, cb_priv, &cleanup_list);
 	mutex_unlock(&flow_indr_block_lock);
 
 	flow_block_indr_notify(&cleanup_list);
@@ -429,32 +430,37 @@ EXPORT_SYMBOL(flow_indr_dev_unregister);
 static void flow_block_indr_init(struct flow_block_cb *flow_block,
 				 struct flow_block_offload *bo,
 				 struct net_device *dev, void *data,
+				 void *cb_priv,
 				 void (*cleanup)(struct flow_block_cb *block_cb))
 {
 	flow_block->indr.binder_type = bo->binder_type;
 	flow_block->indr.data = data;
+	flow_block->indr.cb_priv = cb_priv;
 	flow_block->indr.dev = dev;
 	flow_block->indr.cleanup = cleanup;
 }
 
-static void __flow_block_indr_binding(struct flow_block_offload *bo,
-				      struct net_device *dev, void *data,
-				      void (*cleanup)(struct flow_block_cb *block_cb))
+struct flow_block_cb *flow_indr_block_cb_alloc(flow_setup_cb_t *cb,
+					       void *cb_ident, void *cb_priv,
+					       void (*release)(void *cb_priv),
+					       struct flow_block_offload *bo,
+					       struct net_device *dev, void *data,
+					       void *indr_cb_priv,
+					       void (*cleanup)(struct flow_block_cb *block_cb))
 {
 	struct flow_block_cb *block_cb;
 
-	list_for_each_entry(block_cb, &bo->cb_list, list) {
-		switch (bo->command) {
-		case FLOW_BLOCK_BIND:
-			flow_block_indr_init(block_cb, bo, dev, data, cleanup);
-			list_add(&block_cb->indr.list, &flow_block_indr_list);
-			break;
-		case FLOW_BLOCK_UNBIND:
-			list_del(&block_cb->indr.list);
-			break;
-		}
-	}
+	block_cb = flow_block_cb_alloc(cb, cb_ident, cb_priv, release);
+	if (IS_ERR(block_cb))
+		goto out;
+
+	flow_block_indr_init(block_cb, bo, dev, data, indr_cb_priv, cleanup);
+	list_add(&block_cb->indr.list, &flow_block_indr_list);
+
+out:
+	return block_cb;
 }
+EXPORT_SYMBOL(flow_indr_block_cb_alloc);
 
 int flow_indr_dev_setup_offload(struct net_device *dev,
 				enum tc_setup_type type, void *data,
@@ -465,9 +471,8 @@ int flow_indr_dev_setup_offload(struct net_device *dev,
 
 	mutex_lock(&flow_indr_block_lock);
 	list_for_each_entry(this, &flow_block_indr_dev_list, list)
-		this->cb(dev, this->cb_priv, type, bo);
+		this->cb(dev, this->cb_priv, type, bo, data, cleanup);
 
-	__flow_block_indr_binding(bo, dev, data, cleanup);
 	mutex_unlock(&flow_indr_block_lock);
 
 	return list_empty(&bo->cb_list) ? -EOPNOTSUPP : 0;
diff --git a/net/core/sock.c b/net/core/sock.c
index 6c4acf1f0220..d832c650287c 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -718,7 +718,7 @@ bool sk_mc_loop(struct sock *sk)
 		return inet6_sk(sk)->mc_loop;
 #endif
 	}
-	WARN_ON(1);
+	WARN_ON_ONCE(1);
 	return true;
 }
 EXPORT_SYMBOL(sk_mc_loop);
@@ -1767,6 +1767,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
 		cgroup_sk_alloc(&sk->sk_cgrp_data);
 		sock_update_classid(&sk->sk_cgrp_data);
 		sock_update_netprioidx(&sk->sk_cgrp_data);
+		sk_tx_queue_clear(sk);
 	}
 
 	return sk;
@@ -1990,6 +1991,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		 */
 		sk_refcnt_debug_inc(newsk);
 		sk_set_socket(newsk, NULL);
+		sk_tx_queue_clear(newsk);
 		RCU_INIT_POINTER(newsk->sk_wq, NULL);
 
 		if (newsk->sk_prot->sockets_allocated)
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 90f44f382115..3c45f99e26d5 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -462,6 +462,7 @@ struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp)
 	xdpf->len = totsize - metasize;
 	xdpf->headroom = 0;
 	xdpf->metasize = metasize;
+	xdpf->frame_sz = PAGE_SIZE;
 	xdpf->mem.type = MEM_TYPE_PAGE_ORDER0;
 
 	xsk_buff_free(xdp);